Overview

This notebook gives a general overview of the features included in the dataset.

Show imports Hide imports

%load_ext autoreload
%autoreload 2
import os

import dimcat as dc
import pandas as pd
import plotly.express as px
from dimcat import filters, plotting
from IPython.display import display

import utils

RESULTS_PATH = os.path.abspath(os.path.join(utils.OUTPUT_FOLDER, "overview"))
os.makedirs(RESULTS_PATH, exist_ok=True)


def make_output_path(
    filename: str,
    extension=None,
    path=RESULTS_PATH,
) -> str:
    return utils.make_output_path(filename=filename, extension=extension, path=path)


def save_figure_as(
    fig, filename, formats=("png", "pdf"), directory=RESULTS_PATH, **kwargs
):
    if formats is not None:
        for fmt in formats:
            plotting.write_image(fig, filename, directory, format=fmt, **kwargs)
    else:
        plotting.write_image(fig, filename, directory, **kwargs)

Loading data

D = utils.get_dataset("bach_en_fr_suites", corpus_release="v2.2")
package = D.inputs.get_package()
package_info = package._package.custom
git_tag = package_info.get("git_tag")
utils.print_heading("Data and software versions")
print("J.S. Bach – English and French Suites version v2.2")
print(f"Datapackage '{package.package_name}' @ {git_tag}")
print(f"dimcat version {dc.__version__}\n")
D

Data and software versions
--------------------------

J.S. Bach – English and French Suites version v2.2
Datapackage 'bach_en_fr_suites' @ v2.2
dimcat version 3.4.0

Dataset
=======
{'inputs': {'basepath': None,
            'packages': {'bach_en_fr_suites': ["'bach_en_fr_suites.measures' (MuseScoreFacetName.MuseScoreMeasures)",
                                               "'bach_en_fr_suites.notes' (MuseScoreFacetName.MuseScoreNotes)",
                                               "'bach_en_fr_suites.expanded' (MuseScoreFacetName.MuseScoreHarmonies)",
                                               "'bach_en_fr_suites.chords' (MuseScoreFacetName.MuseScoreChords)",
                                               "'bach_en_fr_suites.metadata' (FeatureName.Metadata)"]}},
 'outputs': {'basepath': None, 'packages': {}},
 'pipeline': []}

filtered_D = filters.HasHarmonyLabelsFilter(keep_values=[True]).process(D)
all_metadata = filtered_D.get_metadata()
assert len(all_metadata) > 0, "No pieces selected for analysis."
all_metadata

		TimeSig	KeySig	last_mc	last_mn	length_qb	last_mc_unfolded	last_mn_unfolded	length_qb_unfolded	volta_mcs	all_notes_qb	...	originalFormat	wikidata	musicbrainz	viaf	imslp	pdf	staff_1_instrument	staff_1_ambitus	staff_2_instrument	staff_2_ambitus
corpus	piece
bach_en_fr_suites	BWV806_01_Prelude	{1: '12/8'}	{1: 3}	37	37	222.0	74	74	444.0	()	673.25	...	capx	https://www.wikidata.org/wiki/Q20645323	https://musicbrainz.org/work/2591954a-1e63-326...	https://viaf.org/viaf/175367933/	https://imslp.org/wiki/English_Suite_No.1_in_A...	https://imslp.org/wiki/Special:ReverseLookup/2094	Piano	56-84 (G#3-C6)	Piano	37-76 (C#2-E5)
	BWV806_02_Allemande	{1: '4/4'}	{1: 3}	34	32	128.0	68	64	256.0	()	498.50	...	capx	https://www.wikidata.org/wiki/Q20645323	https://musicbrainz.org/work/904478b9-c079-35f...	https://viaf.org/viaf/175367933/	https://imslp.org/wiki/English_Suite_No.1_in_A...	https://imslp.org/wiki/Special:ReverseLookup/2094	Piano	44-83 (G#2-B5)	Piano	35-71 (B1-B4)
	BWV806_03_Courante_I	{1: '3/2'}	{1: 3}	22	20	120.0	44	40	240.0	()	381.00	...	capx	https://www.wikidata.org/wiki/Q20645323	https://musicbrainz.org/work/c54e9412-5c9a-373...	https://viaf.org/viaf/175367933/	https://imslp.org/wiki/English_Suite_No.1_in_A...	https://imslp.org/wiki/Special:ReverseLookup/2094	Piano	57-83 (A3-B5)	Piano	33-71 (A1-B4)
	BWV806_04_Courante_II	{1: '3/2'}	{1: 3}	26	24	144.0	52	48	288.0	()	434.50	...	capx	https://www.wikidata.org/wiki/Q20645323	https://musicbrainz.org/work/4ed9eaa4-c831-312...	https://viaf.org/viaf/175367933/	https://imslp.org/wiki/English_Suite_No.1_in_A...	https://imslp.org/wiki/Special:ReverseLookup/2094	Piano	56-83 (G#3-B5)	Piano	33-64 (A1-E4)
	BWV806_05_Double_I	{1: '3/2'}	{1: 3}	26	24	144.0	52	48	288.0	()	392.50	...	capx	https://www.wikidata.org/wiki/Q20645323	https://musicbrainz.org/work/4ed9eaa4-c831-312...	https://viaf.org/viaf/175367933/	https://imslp.org/wiki/English_Suite_No.1_in_A...	https://imslp.org/wiki/Special:ReverseLookup/2094	Piano	61-83 (C#4-B5)	Piano	33-69 (A1-A4)
	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
	BWV817_04_Gavotte	{1: '2/2'}	{1: 4}	22	20	80.0	44	40	160.0	()	226.00	...	capx	https://www.wikidata.org/wiki/Q20645365	https://musicbrainz.org/work/90f3c67a-528d-36e...	https://viaf.org/viaf/174207011/	https://imslp.org/wiki/French_Suite_No.6_in_E_...	https://imslp.org/wiki/Special:ReverseLookup/2105	Piano	63-83 (D#4-B5)	Piano	40-64 (E2-E4)
	BWV817_05_Polonaise	{1: '3/4'}	{1: 4}	24	24	72.0	48	48	144.0	()	144.00	...	capx	https://www.wikidata.org/wiki/Q20645365	https://musicbrainz.org/work/c6632594-2267-323...	https://viaf.org/viaf/174207011/	https://imslp.org/wiki/French_Suite_No.6_in_E_...	https://imslp.org/wiki/Special:ReverseLookup/2105	Piano	64-83 (E4-B5)	Piano	37-64 (C#2-E4)
	BWV817_06_Bourree	{1: '2/2'}	{1: 4}	44	42	168.0	88	84	336.0	()	332.00	...	capx	https://www.wikidata.org/wiki/Q20645365	https://musicbrainz.org/work/d8a68c73-ef63-3f2...	https://viaf.org/viaf/174207011/	https://imslp.org/wiki/French_Suite_No.6_in_E_...	https://imslp.org/wiki/Special:ReverseLookup/2105	Piano	63-83 (D#4-B5)	Piano	35-68 (B1-G#4)
	BWV817_07_Gigue	{1: '6/8'}	{1: 4}	50	48	144.0	100	96	288.0	()	270.50	...	capx	https://www.wikidata.org/wiki/Q20645365	https://musicbrainz.org/work/6119f93a-d4fe-371...	https://viaf.org/viaf/174207011/	https://imslp.org/wiki/French_Suite_No.6_in_E_...	https://imslp.org/wiki/Special:ReverseLookup/2105	Piano	59-83 (B3-B5)	Piano	37-66 (C#2-F#4)
	BWV817_08_Menuett	{1: '3/4'}	{1: 4}	24	24	72.0	48	48	144.0	()	140.00	...	capx	https://www.wikidata.org/wiki/Q20645365	https://musicbrainz.org/work/a500b14f-177c-3d8...	https://viaf.org/viaf/174207011/	https://imslp.org/wiki/French_Suite_No.6_in_E_...	https://imslp.org/wiki/Special:ReverseLookup/2105	Piano	56-81 (G#3-A5)	Piano	40-61 (E2-C#4)

89 rows × 56 columns

mean_composition_years = utils.corpus_mean_composition_years(all_metadata)
chronological_order = mean_composition_years.index.to_list()
corpus_colors = dict(zip(chronological_order, utils.CORPUS_COLOR_SCALE))
corpus_names = {
    corp: utils.get_corpus_display_name(corp) for corp in chronological_order
}
chronological_corpus_names = list(corpus_names.values())
corpus_name_colors = {
    corpus_names[corp]: color for corp, color in corpus_colors.items()
}

mean_composition_years

corpus
bach_en_fr_suites    1721.61236
Name: mean_composition_year, dtype: float64

Composition dates

This section relies on the dataset’s metadata.

valid_composed_start = pd.to_numeric(all_metadata.composed_start, errors="coerce")
valid_composed_end = pd.to_numeric(all_metadata.composed_end, errors="coerce")
print(
    f"Composition dates range from {int(valid_composed_start.min())} {valid_composed_start.idxmin()} "
    f"to {int(valid_composed_end.max())} {valid_composed_end.idxmax()}."
)

Composition dates range from 1722 ('bach_en_fr_suites', 'BWV812_01_Allemande') to 1725 ('bach_en_fr_suites', 'BWV812_01_Allemande').

Mean composition years per corpus

def make_summary(metadata_df):
    piece_is_annotated = metadata_df.label_count > 0
    return metadata_df[piece_is_annotated].copy()

Show source Hide source

summary = make_summary(all_metadata)
bar_data = pd.concat(
    [
        mean_composition_years.rename("year"),
        summary.groupby(level="corpus").size().rename("pieces"),
    ],
    axis=1,
).reset_index()

N = len(summary)
fig = px.bar(
    bar_data,
    x="year",
    y="pieces",
    color="corpus",
    color_discrete_map=corpus_colors,
    title=f"Temporal coverage of the {N} annotated pieces in the Distant Listening Corpus",
)
fig.update_traces(width=5)
fig.update_layout(**utils.STD_LAYOUT)
fig.update_traces(width=5)
save_figure_as(fig, "pieces_timeline_bars")
fig.show()

summary

		TimeSig	KeySig	last_mc	last_mn	length_qb	last_mc_unfolded	last_mn_unfolded	length_qb_unfolded	volta_mcs	all_notes_qb	...	originalFormat	wikidata	musicbrainz	viaf	imslp	pdf	staff_1_instrument	staff_1_ambitus	staff_2_instrument	staff_2_ambitus
corpus	piece
bach_en_fr_suites	BWV806_01_Prelude	{1: '12/8'}	{1: 3}	37	37	222.0	74	74	444.0	()	673.25	...	capx	https://www.wikidata.org/wiki/Q20645323	https://musicbrainz.org/work/2591954a-1e63-326...	https://viaf.org/viaf/175367933/	https://imslp.org/wiki/English_Suite_No.1_in_A...	https://imslp.org/wiki/Special:ReverseLookup/2094	Piano	56-84 (G#3-C6)	Piano	37-76 (C#2-E5)
	BWV806_02_Allemande	{1: '4/4'}	{1: 3}	34	32	128.0	68	64	256.0	()	498.50	...	capx	https://www.wikidata.org/wiki/Q20645323	https://musicbrainz.org/work/904478b9-c079-35f...	https://viaf.org/viaf/175367933/	https://imslp.org/wiki/English_Suite_No.1_in_A...	https://imslp.org/wiki/Special:ReverseLookup/2094	Piano	44-83 (G#2-B5)	Piano	35-71 (B1-B4)
	BWV806_03_Courante_I	{1: '3/2'}	{1: 3}	22	20	120.0	44	40	240.0	()	381.00	...	capx	https://www.wikidata.org/wiki/Q20645323	https://musicbrainz.org/work/c54e9412-5c9a-373...	https://viaf.org/viaf/175367933/	https://imslp.org/wiki/English_Suite_No.1_in_A...	https://imslp.org/wiki/Special:ReverseLookup/2094	Piano	57-83 (A3-B5)	Piano	33-71 (A1-B4)
	BWV806_04_Courante_II	{1: '3/2'}	{1: 3}	26	24	144.0	52	48	288.0	()	434.50	...	capx	https://www.wikidata.org/wiki/Q20645323	https://musicbrainz.org/work/4ed9eaa4-c831-312...	https://viaf.org/viaf/175367933/	https://imslp.org/wiki/English_Suite_No.1_in_A...	https://imslp.org/wiki/Special:ReverseLookup/2094	Piano	56-83 (G#3-B5)	Piano	33-64 (A1-E4)
	BWV806_05_Double_I	{1: '3/2'}	{1: 3}	26	24	144.0	52	48	288.0	()	392.50	...	capx	https://www.wikidata.org/wiki/Q20645323	https://musicbrainz.org/work/4ed9eaa4-c831-312...	https://viaf.org/viaf/175367933/	https://imslp.org/wiki/English_Suite_No.1_in_A...	https://imslp.org/wiki/Special:ReverseLookup/2094	Piano	61-83 (C#4-B5)	Piano	33-69 (A1-A4)
	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
	BWV817_04_Gavotte	{1: '2/2'}	{1: 4}	22	20	80.0	44	40	160.0	()	226.00	...	capx	https://www.wikidata.org/wiki/Q20645365	https://musicbrainz.org/work/90f3c67a-528d-36e...	https://viaf.org/viaf/174207011/	https://imslp.org/wiki/French_Suite_No.6_in_E_...	https://imslp.org/wiki/Special:ReverseLookup/2105	Piano	63-83 (D#4-B5)	Piano	40-64 (E2-E4)
	BWV817_05_Polonaise	{1: '3/4'}	{1: 4}	24	24	72.0	48	48	144.0	()	144.00	...	capx	https://www.wikidata.org/wiki/Q20645365	https://musicbrainz.org/work/c6632594-2267-323...	https://viaf.org/viaf/174207011/	https://imslp.org/wiki/French_Suite_No.6_in_E_...	https://imslp.org/wiki/Special:ReverseLookup/2105	Piano	64-83 (E4-B5)	Piano	37-64 (C#2-E4)
	BWV817_06_Bourree	{1: '2/2'}	{1: 4}	44	42	168.0	88	84	336.0	()	332.00	...	capx	https://www.wikidata.org/wiki/Q20645365	https://musicbrainz.org/work/d8a68c73-ef63-3f2...	https://viaf.org/viaf/174207011/	https://imslp.org/wiki/French_Suite_No.6_in_E_...	https://imslp.org/wiki/Special:ReverseLookup/2105	Piano	63-83 (D#4-B5)	Piano	35-68 (B1-G#4)
	BWV817_07_Gigue	{1: '6/8'}	{1: 4}	50	48	144.0	100	96	288.0	()	270.50	...	capx	https://www.wikidata.org/wiki/Q20645365	https://musicbrainz.org/work/6119f93a-d4fe-371...	https://viaf.org/viaf/174207011/	https://imslp.org/wiki/French_Suite_No.6_in_E_...	https://imslp.org/wiki/Special:ReverseLookup/2105	Piano	59-83 (B3-B5)	Piano	37-66 (C#2-F#4)
	BWV817_08_Menuett	{1: '3/4'}	{1: 4}	24	24	72.0	48	48	144.0	()	140.00	...	capx	https://www.wikidata.org/wiki/Q20645365	https://musicbrainz.org/work/a500b14f-177c-3d8...	https://viaf.org/viaf/174207011/	https://imslp.org/wiki/French_Suite_No.6_in_E_...	https://imslp.org/wiki/Special:ReverseLookup/2105	Piano	56-81 (G#3-A5)	Piano	40-61 (E2-C#4)

89 rows × 56 columns

Composition years histogram

Show source Hide source

hist_data = summary.reset_index()
hist_data.corpus = hist_data.corpus.map(corpus_names)
fig = px.histogram(
    hist_data,
    x="composed_end",
    color="corpus",
    labels=dict(
        composed_end="decade",
        count="pieces",
    ),
    color_discrete_map=corpus_name_colors,
    title=f"Temporal coverage of the {N} annotated pieces in the Distant Listening Corpus",
)
fig.update_traces(xbins=dict(size=10))
fig.update_layout(**utils.STD_LAYOUT)
fig.update_legends(font=dict(size=16))
save_figure_as(fig, "pieces_timeline_histogram", height=1250)
fig.show()

Dimensions

Overview

def make_overview_table(groupby, group_name="pieces"):
    n_groups = groupby.size().rename(group_name)
    absolute_numbers = dict(
        measures=groupby.last_mn.sum(),
        length=groupby.length_qb.sum(),
        notes=groupby.n_onsets.sum(),
        labels=groupby.label_count.sum(),
    )
    absolute = pd.DataFrame.from_dict(absolute_numbers)
    absolute = pd.concat([n_groups, absolute], axis=1)
    sum_row = pd.DataFrame(absolute.sum(), columns=["sum"]).T
    absolute = pd.concat([absolute, sum_row])
    return absolute


absolute = make_overview_table(summary.groupby("workTitle"))
# print(absolute.astype(int).to_markdown())
absolute.astype(int)

	pieces	measures	length	notes	labels
English Suite No. 1	10	317	1462	5587	1198
English Suite No. 2	8	422	1457	6736	1342
English Suite No. 3	8	411	1217	5346	1100
English Suite No. 4	7	292	1239	5894	1069
English Suite No. 5	7	432	1108	6634	1213
English Suite No. 6	8	411	1863	8328	1397
French Suite No. 1	6	164	619	2582	561
French Suite No. 2	6	231	608	2431	713
French Suite No. 3	7	236	746	2953	769
French Suite No. 4	7	200	676	2802	572
French Suite No. 5	7	222	795	3719	704
French Suite No. 6	8	242	816	3386	674
sum	89	3580	12607	56398	11312

def summarize_dataset(D):
    all_metadata = D.get_metadata()
    summary = make_summary(all_metadata)
    return make_overview_table(summary.groupby(level=0))


corpus_summary = summarize_dataset(D)
print(corpus_summary.astype(int).to_markdown())

|                   |   pieces |   measures |   length |   notes |   labels |
|:------------------|---------:|-----------:|---------:|--------:|---------:|
| bach_en_fr_suites |       89 |       3580 |    12607 |   56398 |    11312 |
| sum               |       89 |       3580 |    12607 |   56398 |    11312 |

Measures

all_measures = D.get_feature("measures")
print(
    f"{len(all_measures.index)} measures over {len(all_measures.groupby(level=[0,1]))} files."
)
all_measures.head()

3683 measures over 89 files.

			mc	mn	quarterbeats	duration_qb	keysig	timesig	act_dur	mc_offset	numbering_offset	dont_count	barline	breaks	repeats	next	volta	markers	jump_bwd	jump_fwd	play_until
corpus	piece	i
bach_en_fr_suites	BWV806_01_Prelude	0	1	1	0	6.0	3	12/8	3/2	0	<NA>	<NA>	<NA>	<NA>	firstMeasure	(2,)	<NA>	<NA>	<NA>	<NA>	<NA>
		1	2	2	6	6.0	3	12/8	3/2	0	<NA>	<NA>	<NA>	<NA>	<NA>	(3,)	<NA>	<NA>	<NA>	<NA>	<NA>
		2	3	3	12	6.0	3	12/8	3/2	0	<NA>	<NA>	<NA>	<NA>	<NA>	(4,)	<NA>	<NA>	<NA>	<NA>	<NA>
		3	4	4	18	6.0	3	12/8	3/2	0	<NA>	<NA>	<NA>	<NA>	<NA>	(5,)	<NA>	<NA>	<NA>	<NA>	<NA>
		4	5	5	24	6.0	3	12/8	3/2	0	<NA>	<NA>	<NA>	<NA>	<NA>	(6,)	<NA>	<NA>	<NA>	<NA>	<NA>

all_measures.get_default_analysis().plot_grouped()

Harmony labels

All symbols, independent of the local key (the mode of which changes their semantics).

try:
    all_annotations = D.get_feature("harmonylabels").df
except Exception:
    all_annotations = pd.DataFrame()
n_annotations = len(all_annotations.index)
includes_annotations = n_annotations > 0
if includes_annotations:
    display(all_annotations.head())
    print(f"Concatenated annotation tables contains {all_annotations.shape[0]} rows.")
    no_chord = all_annotations.root.isna()
    if no_chord.sum() > 0:
        print(
            f"{no_chord.sum()} of them are not chords. Their values are:"
            f" {all_annotations.label[no_chord].value_counts(dropna=False).to_dict()}"
        )
    all_chords = all_annotations[~no_chord].copy()
    print(
        f"Dataset contains {all_chords.shape[0]} tokens and {len(all_chords.chord.unique())} types over "
        f"{len(all_chords.groupby(level=[0,1]))} documents."
    )
    all_annotations["corpus_name"] = all_annotations.index.get_level_values(0).map(
        utils.get_corpus_display_name
    )
    all_chords["corpus_name"] = all_chords.index.get_level_values(0).map(
        utils.get_corpus_display_name
    )
else:
    print("Dataset contains no annotations.")

			mc	mn	quarterbeats	duration_qb	mc_onset	mn_onset	timesig	staff	voice	volta	...	numeral_or_applied_to_numeral	intervals_over_bass	intervals_over_root	scale_degrees	scale_degrees_and_mode	scale_degrees_major	scale_degrees_minor	globalkey	localkey	chord
corpus	piece	i
bach_en_fr_suites	BWV806_01_Prelude	0	1	1	0	1.5	0	0	12/8	2	1	<NA>	...	I	(M3, P5)	(M3, P5)	(1, 3, 5)	(1, 3, 5), major	(1, 3, 5)	(1, #3, 5)	A	I	I
		1	1	1	3/2	1.5	3/8	3/8	12/8	2	1	<NA>	...	V	(M3, P5, m7)	(M3, P5, m7)	(5, 7, 2, 4)	(5, 7, 2, 4), major	(5, 7, 2, 4)	(5, #7, 2, 4)	A	I	V7
		2	1	1	3	1.5	3/4	3/4	12/8	2	1	<NA>	...	I	(M3, P5)	(M3, P5)	(1, 3, 5)	(1, 3, 5), major	(1, 3, 5)	(1, #3, 5)	A	I	I
		3	1	1	9/2	1.5	9/8	9/8	12/8	2	1	<NA>	...	V	(M3, P5, m7)	(M3, P5, m7)	(5, 7, 2, 4)	(5, 7, 2, 4), major	(5, 7, 2, 4)	(5, #7, 2, 4)	A	I	V7
		4	2	2	6	1.5	0	0	12/8	2	1	<NA>	...	I	(M3, P5)	(M3, P5)	(1, 3, 5)	(1, 3, 5), major	(1, 3, 5)	(1, #3, 5)	A	I	I

5 rows × 51 columns

Concatenated annotation tables contains 11158 rows.
Dataset contains 11158 tokens and 786 types over 89 documents.